Certifying and Removing Disparate Impact

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, Suresh Venkatasubramanian

2015 · 1.8K citations · 18 references

Concepts

Abstract

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender) and an explicit description of the process.

References

18